Automatic Detection of Incorrect Location Images Uploaded by Users

Hsu Yung Cheng, Chih Chang Yu, Hsiang Yuan Liu, Sih Ying Chen

研究成果: 書貢獻/報告類型會議論文篇章同行評審

摘要

This paper proposes a system to automatically perform classification and data cleaning on location images in a database contributed by arbitrary users. Since human inspection is not feasible for large-scale databases, the ability to detect incorrect scenes uploaded by users is very important to maintain the correctness of the database. In this work, we compare different feature extractors using deep convolutional networks trained by massive datasets. Also, a detector is designed to identify incorrect scenes that can overcome the challenges of large intra-cluster distances. The experiments have validated the effectiveness of the proposed approach on a very challenging dataset.

原文???core.languages.en_GB???
主出版物標題IEEE 21st International Workshop on Multimedia Signal Processing, MMSP 2019
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781728118178
DOIs
出版狀態已出版 - 9月 2019
事件21st IEEE International Workshop on Multimedia Signal Processing, MMSP 2019 - Kuala Lumpur, Malaysia
持續時間: 27 9月 201929 9月 2019

出版系列

名字IEEE 21st International Workshop on Multimedia Signal Processing, MMSP 2019

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???21st IEEE International Workshop on Multimedia Signal Processing, MMSP 2019
國家/地區Malaysia
城市Kuala Lumpur
期間27/09/1929/09/19

指紋

深入研究「Automatic Detection of Incorrect Location Images Uploaded by Users」主題。共同形成了獨特的指紋。

引用此